Compatible with every major AI agent and IDE
What is the ShipBob MCP Server?
Connect your ShipBob account to any AI agent and take full control of your e-commerce fulfillment and supply chain through natural conversation.
What you can do
- Order Management — List, retrieve, and create fulfillment orders. Check real-time statuses and cancel orders when necessary.
- Product Catalog — Manage your virtual product records, list variants, and convert items into bundles directly from the chat.
- Inventory Tracking — Monitor inventory levels across different locations, check lot-specific data, and query historical inventory movements.
- Shipment Visibility — Get detailed tracking information and update shipment addresses to ensure successful deliveries.
- Returns & Receiving — Create and manage return orders and Warehouse Receiving Orders (WRO) to keep your supply chain moving.
How it works
- Subscribe to this server
- Enter your ShipBob API Token
- Start managing your logistics from Claude, Cursor, or any MCP-compatible client
No more switching between your store backend and ShipBob dashboard to check if an order has shipped. Your AI acts as a dedicated logistics coordinator.
Who is this for?
- E-commerce Owners — quickly check stock levels and order statuses without digging through complex dashboards
- Customer Support Teams — retrieve tracking numbers and update shipping addresses instantly to resolve customer inquiries
- Operations Managers — monitor warehouse receiving and inventory history to optimize supply chain workflows
Built-in capabilities (30)
Cancel multiple shipments at once
Mark tracking as synced to your system
Cancel an order and its shipments
Convert a variant into a bundle
Create a new fulfillment order
Create a new product with variants
Create a new Warehouse Receiving Order (WRO)
Create a return order (RMA)
Get aggregated inventory levels across all locations
Get inventory levels grouped by fulfillment center
Get inventory levels grouped by lot/expiration
Get order details and shipment status
Get details for a specific product
Get PDF box labels for a WRO
Get specific shipment details
g., a Shopify store). List all channels the user has access to
List all inventory items
List invoices by date range
List orders with status/tracking filters
List all variants for a product
List products with filtering
List Warehouse Receiving Orders (WROs)
List return orders
List available fee types
Query inventory movement events
Search transactions (charges, credits)
Mark WROs as synced to your system
Update product details
Update an existing return
Update the shipping address for a shipment
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 30 tools from ShipBob through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries ShipBob, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
ShipBob in OpenAI Agents SDK
ShipBob and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect ShipBob to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for ShipBob in OpenAI Agents SDK
The ShipBob MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 30 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
ShipBob for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the ShipBob MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check the status of a specific order using its ID?
Yes! Use the get_order tool with the Order ID. Your agent will return the current fulfillment status, tracking information, and shipment details associated with that order.
How do I see current inventory levels across different warehouse locations?
You can use the get_inventory_levels_by_location tool. It provides a breakdown of on-hand, fulfillable, and committed inventory for each ShipBob fulfillment center.
Is it possible to cancel an order through the AI agent?
Yes, if the order is in a cancellable state, you can use the cancel_order tool by providing the Order ID to stop the fulfillment process.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Billplz
11 toolsManage your payment collections via Billplz — list collections, bills, and transactions directly from any AI agent.

Microsoft Teams Events
10 toolsOrganize webinars and virtual events through Microsoft Teams with registration, attendee tracking, and engagement features.

BL.INK
10 toolsManage enterprise links via BL.INK — shorten URLs, track analytics, and manage branded domains directly from any AI agent.

Boeing Developer Tools
10 toolsGlobal aviation intelligence, Jeppesen aerodromes, and aircraft models.
